Survey details methodologies for accelerating deep learning on heterogeneous architectures

This paper provides a comprehensive survey of methodologies and tools designed to accelerate deep learning on heterogeneous architectures. It covers hardware-software co-design, automated synthesis, domain-specific compilers, and design space exploration. The review aims to offer a broad perspective on the rapidly evolving field of deep learning accelerators, highlighting technical challenges and future research directions. AI

IMPACT Provides a structured overview of techniques for optimizing AI model performance on diverse hardware.

RANK_REASON The item is a survey paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• approximate computing
• arXiv
• computer architecture
• Cristina Silvano
• deep learning
• edge platforms
• hardware architecture
• Heterogeneous Architectures Programming Library
• high-performance computing
• machine learning

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →